51 lines
1.0 KiB
Markdown
51 lines
1.0 KiB
Markdown
|
# mnists
|
||
|
|
||
|
downloads and prepares various mnist-compatible datasets.
|
||
|
|
||
|
files are downloaded to `~/.mnist` and checked for integrity by sha256 hashes.
|
||
|
|
||
|
**dependencies:** numpy
|
||
|
|
||
|
**install:** `pip install --upgrade --upgrade-strategy only-if-needed mnists`
|
||
|
|
||
|
I've added --upgrade-strategy to the command-line
|
||
|
so you don't accidentally "upgrade" numpy to
|
||
|
a version not compiled specifically for your system.
|
||
|
|
||
|
## usage
|
||
|
|
||
|
```python
|
||
|
import mnists
|
||
|
|
||
|
dataset = "emnist_balanced"
|
||
|
train_images, train_labels, test_images, test_labels = mnists.prepare(dataset)
|
||
|
```
|
||
|
|
||
|
the default output shape is (n, 1, 28, 28).
|
||
|
pass `flatten=True` to `mnists.prepare` to get (n, 784).
|
||
|
|
||
|
## datasets
|
||
|
|
||
|
in alphabetical order:
|
||
|
|
||
|
### [emnist][emnist]
|
||
|
|
||
|
* `emnist_balanced`
|
||
|
* `emnist_byclass`
|
||
|
* `emnist_bymerge`
|
||
|
* `emnist_digits`
|
||
|
* `emnist_letters`
|
||
|
* `emnist_mnist`
|
||
|
|
||
|
### [fashion-mnist][fashion-mnist]
|
||
|
|
||
|
* `fashion_mnist`
|
||
|
|
||
|
### [mnist][mnist]
|
||
|
|
||
|
* `mnist`
|
||
|
|
||
|
[emnist]: //www.nist.gov/itl/iad/image-group/emnist-dataset
|
||
|
[fashion-mnist]: //github.com/zalandoresearch/fashion-mnist
|
||
|
[mnist]: http://yann.lecun.com/exdb/mnist/
|